Showing 1–18 of 18 results
/ Date/ Name
Nov 27, 2024SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?Aug 8, 2023Backdoor Federated Learning by Poisoning Backdoor-Critical LayersApr 2, 2026Reliable Control-Point Selection for Steering Reasoning in Large Language ModelsApr 2, 2026SenseMath: Do LLMs Have Number Sense? Evaluating Shortcut Use, Judgment, and GenerationOct 10, 2025Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVRMar 29, 2023A Pilot Study of Query-Free Adversarial Attack against Stable DiffusionOct 30, 2024Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?Sep 20, 2025ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic InstructionsApr 8, 2026Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMsApr 15, 2026AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI AgentsMay 29, 2025SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language ModelsJun 5, 2025Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision StudyFeb 19, 2025Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive DiagnosisMar 29, 2026Emergent Social Intelligence Risks in Generative Multi-Agent SystemsApr 18, 2023A Comparison of Image Denoising MethodsFeb 20, 2024Defending Jailbreak Prompts via In-Context Adversarial GameApr 1, 2026Dual Optimal: Make Your LLM Peer-like with DignityJun 5, 2025Quasiparticle Interference Kernel Extraction with Variational Autoencoders via Latent Alignment